Azra AI · 1 day ago

Principal Data Scientist

Nashville, TN

Full-time

Remote

Lead/Staff

$136K/yr - $204K/yr

8+ years exp

Maximize your interview chances

Artificial Intelligence (AI)Health Care

Insider Connection @Azra AI

Discover valuable connections within the company who might provide insights and potential referrals.
Get 3x more responses when you reach out via email instead of LinkedIn.

Responsibilities

Lead End-to-End Data Science Process: Oversee all stages of the data science lifecycle, from data acquisition, cleansing, and preparation to exploratory data analysis (EDA), feature engineering, model selection, and validation for healthcare use cases.

Model Development: Design and build predictive models using NLP and Transformer models for analyzing unstructured healthcare data, such as pathology reports, radiology images, and clinical notes, to support fast, data-driven decisions in oncology, cardiology, neurology, and radiology.

AI Image Analysis: Leverage AI techniques for analyzing radiology images (e.g., X-rays, MRIs, CT scans) to detect abnormalities and assist clinicians in diagnostic decisions, integrating these insights into the clinical workflow.

Data Transformation: Prepare and transform large, complex datasets, including millions of clinical reports and medical images, for efficient and scalable model development and deployment.

Feature Engineering and Optimization: Develop innovative feature extraction techniques to optimize model inputs and improve predictive accuracy for healthcare applications.

Model Validation & Verification: Ensure the robustness, accuracy, and clinical relevance of models through rigorous validation and verification protocols.

Collaboration Across Teams: Work closely with product, engineering, and clinical teams to integrate AI models and image analysis tools into the overall healthcare workflow, ensuring that solutions are actionable and scalable in real-world environments.

Proactive QA and Data Integrity Checks: Implement QA processes for ORU and ADT data during customer implementations, ensuring data accuracy and minimizing errors such as incorrect medical record numbers (MRNs).

Cloud Computing and Deployment: Leverage cloud platforms (GCP) to scale and deploy models securely in healthcare settings, maintaining high performance and compliance with regulatory standards.

Qualification

Find out how your skills align with this job's requirements. If anything seems off, you can easily click on the tags to select or unselect skills to reflect your actual expertise.

Data ScienceMachine LearningAI ModelsPythonNLPTransformer ModelsGCPDockerStatistical AnalysisFeature EngineeringHealthcare CompliancePostgreSQLMySQLGit/GitLabStreamlitCollaborative Mindset

Required

Master’s or Ph.D. in Data Science, Computer Science, Statistics, or a related field or equivalent experience.

8+ years of experience in data science, machine learning, and AI, including applied experience in healthcare environments.

Expertise in Python (pandas, numpy, scikit-learn, PyTorch) and hands-on experience with NLP and Transformer models, including Hugging Face and spaCy.

Experience deploying models in cloud environments (GCP or AWS), with an understanding of best practices in scaling AI solutions.

Ability to work cross-functionally with diverse teams, ensuring that AI models and image analysis tools integrate seamlessly into clinical workflows.

Strong knowledge of machine learning techniques, statistical analysis, and training robust and scalable models.

Familiarity with healthcare regulations such as HIPAA and best practices for handling sensitive patient data.

Familiarity with Docker for model deployment.

Preferred

Hands-on experience with AI-driven image analysis techniques, working with radiology images (e.g., X-rays, MRIs, CT scans) to develop and deploy image classification or segmentation models.

Strong knowledge of healthcare data systems, such as EHR/EMR, pathology, radiology, and lab reports, and experience with real-world healthcare applications.

Experience with feature engineering and data validation for real-world clinical applications.